Robust marker tracking algorithm for precise UAV vision-based autonomous landing

Abstract

The robust marker tracking and relative navigation algorithms are presented for precise UA V vision-based autonomous landing. To recognize the marker in close-range, the concentric circles are adopted as the marker with ellipse fitting algorithm based on Direct Least Square. We assume that IMU provides vehicle's attitude and altitude so that we consider GPS-denied situation. Also multiple ellipses are used to estimate its center pixel coordinate makes UA V land more accurately. To verify the vision-based relative navigation algorithm we suggest, numerical simulations are obtained by using virtual reality toolbox in MATLABTM. We predetermine the true position and attitude of UA V, and the result of the relative position calculated from vision software including the filter is compared. The simulation results show that the algorithm is robust and very accurate.

Survey of computer vision algorithms and applications for unmanned aerial vehicles

“…Furthermore, wide variety of different autonomous applications have been presented; such as autonomous take-off and landing ( Cabecinhas, Naldi, Marconi, Silvestre, & Cunha, 2010;Jung, Bang, & Lee, 2015;Lee, Su, Yeah, Huang, & Chen, 2014b;Sanchez-Lopez, Saripalli, Campoy, Pestana, & Fu, 2013 ), autonomous aerial refueling ( Aarti & Jimoh O, 2013;Campa, Napolitano, & Farvolini, 2009;Xufeng, Xinmin, & Xingwei, 2013;Yin et al, 2016 ), autonomous tracking ( Achtelik, Zhang, Kuhnlenz, & Buss, 2009;Lin, Lum, Chen, & Lee, 2009;Martínez Luna, 2013;Zhao, Fei, & Geng, 2013 ) or autonomous route planning ( Govindaraju et al, 2014;Kothari, Postlethwaite, & Gu, 2009;Sangyam, Laohapiengsak, Chongcharoen, & Nilkhamhang, 2010;Yamasaki, Sakaida, Enomoto, Takano, & Baba, 2007;Yang, Qi, Xiao, & Yong, 2014 ), where high levels of accuracy of localization, detection and tracking are required.…”

“…However, the experiments have been limited to simulations. Huan et al, 2015;Jung et al, 2015) Herissé et al (2012 ; Lee et al (2014b) ; Yang et al (2013) ( Beck et al, 2016;Casau, Cabecinhas, & Silvestre, 2011;Wenzel et al, 2011 ) Fixed Wing ( Daibing, Xun, & Weiwei, 2012;Kim et al, 2013;Kong, Zhang, & Zhang, 2015;Kong et al, 2014;Muskardin et al, 2016;Pan, Hu, & Shen, 2015;Pouya & Saghafi, 2009 ) Using aerial imaginary for monitoring and vigilance purposes Traffic ( Cusack & Khaleghparast, 2015;Heintz et al, 2007;Ke et al, 2015; Autonomous Agricultural crop ( Anthony et al, 2014;Navia, Mondragon, Patino, & Colorado, 2016;Tokekar, Hook, Mulla, & Isler, 2016 ) Surveillance Animal protection ( Ward, Hensler, Alsalam, & Gonzalez, 2016;Xu et al, 2015 ) Other ( COE, 2016;Semsch et al, 2009 ) Aerial Refueling the aircrafts during the flight by using a tanker aircraft Boom-and-Receptacle ( CHEN, JIA, & ZHANG, 2010;Mammarella et al, 2010;Williamson et al, 2009;Yuan, Yan, Qu, & Zhao, 2015c ) Inspecting the damages and collapses in the structures for monitoring and maintenance purposes Buildings ( Choi & Kim, 2015b;Eschmann et al, 2012;Nikolic et al, 2013;Omari et al, 2014 ) Bridges ( Chan, Guan, Jo, & Blumenstein, 2015;Hammer, Dumoulin, Vozel, & Che...…”

Precision Landing for Low-Maintenance Remote Operations with UAVs

“…In order to detect the desired landing location, visual markers are usually used. One of the most common is the classic "H" which describes a heliport [47][48][49]. Furthermore, other types of patterns are used for specific cases, such as various circumferences, which may be either concentric [50] or not [51].…”

Autonomous Quadcopter Landing on a Moving Target

“…Computer vision techniques to detect the landing target using onboard cameras was widely studied in literature [ 12 , 13 , 14 , 15 , 16 , 17 ]. Additionally, for landing on moving targets, a number of works have explored coordinated landing with active communication between the UAV and the target [ 18 , 19 , 20 ].…”